x-polyglot-x

x-polyglot-x's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in unsloth/Qwen3.8-27B-GGUF 3 days ago

Qwen3.8-27B only 18 tok/s vs Qwen3.6-27B 62 tok/s on A100 80GB + vLLM — expected?

👍 3

4

#66 opened 3 days ago by

Alecone

New activity in Kwaipilot/KAT-Coder-V2.5-Dev 8 days ago

Still Waiting for Vision 👀

👍❤️ 6

5

#14 opened 22 days ago by

KennyVo

New activity in moonshotai/Kimi-K3 9 days ago

This might be the cheapest GPU type for Kimi K3 with 100% Data-on-GPU — Gift for AMD MI300x8

😎 2

4

#168 opened 10 days ago by

ghostplant

New activity in moonshotai/Kimi-K3 10 days ago

Waste engine: Run the full 2.78T-parameter Kimi K3 on a laptop

🔥 21

26

#148 opened 22 days ago by

marcobambini

New activity in unsloth/Kimi-K3-GGUF 10 days ago

Can i run this on my macbook?

👀🤯 4

5

#5 opened 22 days ago by

hugginface536

New activity in unsloth/MiniMax-M3-GGUF about 2 months ago

tested UD-Q4_K_XL - it is terrible vs DS4F

5

#9 opened 2 months ago by

alexbi29

New activity in freakyskittle/kimi-k2.7-code-GGUF about 2 months ago

cannot download 1-bit and 2-bit. error 400

2

#2 opened 2 months ago by

cocomaker

New activity in unsloth/Kimi-K2.7-Code-GGUF about 2 months ago

Q8_K_XL seems small

1

#10 opened about 2 months ago by

etemiz

New activity in moonshotai/Kimi-K2.7-Code about 2 months ago

Consumer sized versions? (26B A3B Versions)

👍🔥 9

5

#5 opened 2 months ago by

CYISNOTHERE

New activity in moonshotai/Kimi-K2.7-Code 2 months ago

MLX g32 bf16 conversion for TP=2 Mac Studios @20.1 tok/s average

👍 4

5

#7 opened 2 months ago by

whistlercapital

New activity in freakyskittle/kimi-k2.7-code-GGUF 2 months ago

Thank you!

👍 1

1

#1 opened 2 months ago by

x-polyglot-x

New activity in unsloth/Kimi-K2.7-Code-GGUF 2 months ago

Excited for this one!

👍 3

#3 opened 2 months ago by

x-polyglot-x

New activity in unsloth/Step-3.7-Flash-GGUF 3 months ago

How does this model fare?

9

#4 opened 3 months ago by

x-polyglot-x

New activity in unsloth/DeepSeek-V4-Flash 3 months ago

Worse than (smaller) MiniMax M2.7??

17

#2 opened 4 months ago by deleted

New activity in mlx-community/Kimi-K2.6-MoE-Smart-Quant 3 months ago

Is the model conversion done?

👍👀 3

2

#1 opened 3 months ago by

Seth-TW

New activity in unsloth/Qwen3.5-397B-A17B-MTP-GGUF 3 months ago

Spec-type is never recognized (Mac)

#4 opened 3 months ago by

x-polyglot-x

New activity in batiai/DeepSeek-V4-Pro-GGUF 3 months ago

Question on quantization

1

#1 opened 3 months ago by

x-polyglot-x

New activity in antirez/deepseek-v4-gguf 3 months ago

RPC server possible?

#8 opened 3 months ago by

x-polyglot-x

New activity in unsloth/Qwen3.6-27B-MTP-GGUF 3 months ago

Stable MTP first release!

❤️ 15

11

#6 opened 3 months ago by

danielhanchen

New activity in deepseek-ai/DeepSeek-V4-Flash 3 months ago

How can I use this with llama.cpp?

➕ 2

7

#24 opened 4 months ago by

KeilahElla